Molmo 2 8B vs Qwen3.8-Max

Qwen3.8-Max leads on the Visual Intelligence Index by 16.2 points, and Molmo 2 8B scores higher on 1 of the 7 benchmarks where the two differ.

Model

Compared with

At a glance

Measure	Molmo 2 8B	Qwen3.8-Max
Visual Intelligence Index	57.6%	73.8%
Rank	#9 of 9	#4 of 9
Cost per taskMean over the benchmarks, at list price.	—	$0.151
Latency per taskEach benchmark's median, averaged.	62.2s	66.0s
Tokens per task	12,048	68,932
Input / 1M tokens	—	$2.00
Output / 1M tokens	—	$6.00
Context window	37K	1M
Availability	Open weights	Proprietary

Each capability index is a weighted mean of the benchmarks that contribute to the capability.

Capability	Molmo 2 8B	Qwen3.8-Max	Lead
Perception	58.7%	72.0%	−13.3
Spatial Reasoning	61.0%	74.3%	−13.3
Temporal Reasoning	57.5%	73.6%	−16.0
Action / Event Understanding	51.1%	71.5%	−20.4
Causal Reasoning	61.7%	78.2%	−16.5
Information Retrieval	52.1%	72.0%	−19.8

Benchmark	Molmo 2 8B	Qwen3.8-Max	Lead
Video-MME v2	27.5%	60.2%	−32.7
LVBench	48.6%	58.9%	−10.3
Perception Test	67.4%	83.9%	−16.5
NExT-QA	89.2%	87.6%	+1.7
Q-Bench Video	62.9%	69.0%	−6.1
EgoSchema	58.2%	85.2%	−27.0
UCF101-AD	19.5%	56.5%	−37.0

3.5/ 5

Reachable0.5: There is an endpoint you can call without hosting anything.
First-party API — supported
Third-party API — not supported
Portable1.0: You can run it yourself, and are not tied to one vendor.
Open weights — supported
Self-hostable — supported
Multimodal input0.5: It takes the footage directly, rather than frames you extracted.
Video ingestion — supported
Audio — not supported
Programmable1.0: Output you can parse, and tools it can call on its own.
Structured output — supported
Tool calling — supported
Operable0.5: Usable interactively and in bulk, not only one call at a time.
Streaming — supported
Batch API — not supported

3.5/ 5

Reachable1.0: There is an endpoint you can call without hosting anything.
First-party API — supported
Third-party API — supported
Portable0.0: You can run it yourself, and are not tied to one vendor.
Open weights — not supported
Self-hostable — not supported
Multimodal input0.5: It takes the footage directly, rather than frames you extracted.
Video ingestion — supported
Audio — not supported
Programmable1.0: Output you can parse, and tools it can call on its own.
Structured output — supported
Tool calling — supported
Operable1.0: Usable interactively and in bulk, not only one call at a time.
Streaming — supported
Batch API — supported